TensorRT-LLM icon indicating copy to clipboard operation
TensorRT-LLM copied to clipboard
verified publisher icon NVIDIA

pass rotary_emb_base to gpt_attention

Open FightingMan opened this issue 2 years ago • 0 comments

1.pass rotary_emb_base to gpt attention tensorrt_llm/models/qwen/model.py 2.change variable name： rotary_base -> rotary_emb_base examples/qwen/build.py

FightingMan avatar Dec 08 '23 13:12 FightingMan